Instructions to use gagan3012/Florence-2-FT-ArabicOCR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gagan3012/Florence-2-FT-ArabicOCR with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="gagan3012/Florence-2-FT-ArabicOCR", trust_remote_code=True)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("gagan3012/Florence-2-FT-ArabicOCR", trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained("gagan3012/Florence-2-FT-ArabicOCR", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gagan3012/Florence-2-FT-ArabicOCR with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gagan3012/Florence-2-FT-ArabicOCR"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gagan3012/Florence-2-FT-ArabicOCR",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/gagan3012/Florence-2-FT-ArabicOCR

SGLang

How to use gagan3012/Florence-2-FT-ArabicOCR with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "gagan3012/Florence-2-FT-ArabicOCR" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gagan3012/Florence-2-FT-ArabicOCR",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "gagan3012/Florence-2-FT-ArabicOCR" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gagan3012/Florence-2-FT-ArabicOCR",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use gagan3012/Florence-2-FT-ArabicOCR with Docker Model Runner:
```
docker model run hf.co/gagan3012/Florence-2-FT-ArabicOCR
```

Model Card for Florence-2-FT-ArabicOCR

Florence-2 for ArabicOCR

Usage

import requests

from PIL import Image
from transformers import AutoProcessor, AutoModelForCausalLM 


model = AutoModelForCausalLM.from_pretrained("gagan3012/Florence-2-FT-ArabicOCR", trust_remote_code=True)
processor = AutoProcessor.from_pretrained("gagan3012/Florence-2-FT-ArabicOCR", trust_remote_code=True)

prompt = "<ArabicOCR>"

url = "https://huggingface.co/proxy/datasets-server.huggingface.co/cached-assets/Fakhraddin/khatt/--/a3236e1dee690fbb4ce9ceadac24b2be375f5503/--/default/validation/0/image/image.jpg?Expires=1719446453&Signature=WaBqdA7YWlwmyVFf~Nr4l0Qm6uM34p9e7Df4GPLNA93qhg7VS3JgZpqHvHWA3ZRqaz7JbPANNSrEv27lskSAGcZ6ow168Lv2Yzkemv87mA6sbED9UqTQAyeSWgCZ6z-3OUHLIfHRtrlsSetKDSyhKSYhIHARx8tI-Z35wOhTXnPDWbq63rtrFQ1YFc~u-YzETwn7SWqXO-NJpl-JZ~xPSbYHzrDQtZgFxnrC~aEyVzJXdfdQ8v7AxzRoz5I6ISimDADy-KGu0d6LuYd3eAwf-LWwGbLEeNYtMZgevRJIFeDxi-75lYitmxiVG0BLfNFtJAJGYvjpeLsug0cIwo-pAg__&Key-Pair-Id=K3EI6M078Z3AC3"
image = Image.open(requests.get(url, stream=True).raw)

if image.mode != "RGB":
    image = image.convert("RGB")

inputs = processor(text=prompt, images=image, return_tensors="pt")

generated_ids = model.generate(
    input_ids=inputs["input_ids"],
    pixel_values=inputs["pixel_values"],
    max_new_tokens=1024,
    do_sample=False,
    num_beams=3
)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]

parsed_answer = processor.post_process_generation(generated_text, task="<ArabicOCR>", image_size=(image.width, image.height))

print(parsed_answer)

Downloads last month: 72

Safetensors

Model size

0.3B params

Tensor type

F32

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

gagan3012
/

Florence-2-FT-ArabicOCR

Model Card for Florence-2-FT-ArabicOCR

Usage

Space using gagan3012/Florence-2-FT-ArabicOCR 1